In [1]:
import torch
import numpy as np
np_data = np.arange(6).reshape((2, 3))
torch_data = torch.from_numpy(np_data)
tensor2array = torch_data.numpy()
print(
'\nnumpy array:', np_data, # [[0 1 2], [3 4 5]]
'\ntorch tensor:', torch_data, # 0 1 2 \n 3 4 5 [torch.LongTensor of size 2x3]
'\ntensor to array:', tensor2array, # [[0 1 2], [3 4 5]]
)
In [3]:
import torch
from torch.autograd import Variable
tensor = torch.FloatTensor([[1,2],[3,4]])
variable = Variable(tensor)
print(tensor)
print(variable)
In [15]:
t_out = torch.mean(tensor * tensor)
print(t_out)
In [17]:
print(variable)
print(variable*variable)
v_out = torch.mean(variable*variable)
print(v_out)
In [18]:
print(v_out.grad)
In [22]:
%matplotlib inline
import torch
import matplotlib.pyplot as plt
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1) # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size()) # noisy y data (tensor), shape=(100, 1)
# 画图
plt.scatter(x.data.numpy(), y.data.numpy())
plt.show()
In [23]:
import torch
import torch.nn.functional as F # 激励函数都在这
class Net(torch.nn.Module): # 继承 torch 的 Module
def __init__(self, n_feature, n_hidden, n_output):
super(Net, self).__init__() # 继承 __init__ 功能
# 定义每层用什么样的形式
self.hidden = torch.nn.Linear(n_feature, n_hidden) # 隐藏层线性输出
self.predict = torch.nn.Linear(n_hidden, n_output) # 输出层线性输出
def forward(self, x): # 这同时也是 Module 中的 forward 功能
# 正向传播输入值, 神经网络分析出输出值
x = F.relu(self.hidden(x)) # 激励函数(隐藏层的线性值)
x = self.predict(x) # 输出值
return x
net = Net(n_feature=1, n_hidden=10, n_output=1)
In [26]:
# optimizer 是训练的工具
optimizer = torch.optim.SGD(net.parameters(), lr=0.2) # 传入 net 的所有参数, 学习率
loss_func = torch.nn.MSELoss() # 预测值和真实值的误差计算公式 (均方差)
for t in range(100):
prediction = net(x) # 喂给 net 训练数据 x, 输出预测值
loss = loss_func(prediction, y) # 计算两者的误差
optimizer.zero_grad() # 清空上一步的残余更新参数值
loss.backward() # 误差反向传播, 计算参数更新值
optimizer.step() # 将参数更新值施加到 net 的 parameters 上
# 接着上面来
if t % 5 == 0:
# plot and show learning process
plt.cla()
plt.scatter(x.data.numpy(), y.data.numpy())
plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
plt.text(0.5, 0, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color': 'red'})
plt.pause(0.1)
In [37]:
import torch
import matplotlib.pyplot as plt
# 假数据
n_data = torch.ones(100, 2) # 数据的基本形态
x0 = torch.normal(2*n_data, 1) # 类型0 x data (tensor), shape=(100, 2)
y0 = torch.zeros(100) # 类型0 y data (tensor), shape=(100, 1)
x1 = torch.normal(-2*n_data, 1) # 类型1 x data (tensor), shape=(100, 1)
y1 = torch.ones(100) # 类型1 y data (tensor), shape=(100, 1)
plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=y.data.numpy(), s=100, lw=0, cmap='RdYlGn')
plt.show()
In [38]:
class Net(torch.nn.Module): # 继承 torch 的 Module
def __init__(self, n_feature, n_hidden, n_output):
super(Net, self).__init__() # 继承 __init__ 功能
self.hidden = torch.nn.Linear(n_feature, n_hidden) # 隐藏层线性输出
self.out = torch.nn.Linear(n_hidden, n_output) # 输出层线性输出
def forward(self, x):
# 正向传播输入值, 神经网络分析出输出值
x = F.relu(self.hidden(x)) # 激励函数(隐藏层的线性值)
x = self.out(x) # 输出值, 但是这个不是预测值, 预测值还需要再另外计算
return x
net = Net(n_feature=2, n_hidden=10, n_output=2) # 几个类别就几个 output
In [41]:
# optimizer 是训练的工具
optimizer = torch.optim.SGD(net.parameters(), lr=0.02) # 传入 net 的所有参数, 学习率
# 算误差的时候, 注意真实值!不是! one-hot 形式的, 而是1D Tensor, (batch,)
# 但是预测值是2D tensor (batch, n_classes)
loss_func = torch.nn.CrossEntropyLoss()
plt.ion() # 画图
plt.show()
for t in range(100):
out = net(x) # 喂给 net 训练数据 x, 输出分析值
loss = loss_func(out, y) # 计算两者的误差
optimizer.zero_grad() # 清空上一步的残余更新参数值
loss.backward() # 误差反向传播, 计算参数更新值
optimizer.step() # 将参数更新值施加到 net 的 parameters 上
# 接着上面来
if t % 2 == 0:
plt.cla()
# 过了一道 softmax 的激励函数后的最大概率才是预测值
prediction = torch.max(F.softmax(out), 1)[1]
pred_y = prediction.data.numpy().squeeze()
target_y = y.data.numpy()
plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=pred_y, s=100, lw=0, cmap='RdYlGn')
accuracy = sum(pred_y == target_y)/200. # 预测中有多少和真实值一样
plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={'size': 20, 'color': 'red'})
plt.pause(0.1)
plt.ioff() # 停止画图
plt.show()
In [67]:
torch.manual_seed(1) # reproducible
# 假数据
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1) # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size()) # noisy y data (tensor), shape=(100, 1)
def save():
# 建网络
net1 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
torch.nn.Linear(10, 1)
)
optimizer = torch.optim.SGD(net1.parameters(), lr=0.5)
loss_func = torch.nn.MSELoss()
# 训练
for t in range(100):
prediction = net1(x)
loss = loss_func(prediction, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
torch.save(net1, 'net.pkl') # 保存整个网络
torch.save(net1.state_dict(), 'net_params.pkl') # 只保存网络中的参数 (速度快, 占内存少)
In [70]:
fig, axes = plt.subplots(1, 2, figsize=(10,3))
def restore_net():
# restore entire net1 to net2
net2 = torch.load('net.pkl')
prediction = net2(x)
axes[0].cla()
axes[0].scatter(x.data.numpy(), y.data.numpy())
axes[0].plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
def restore_params():
# 新建 net3
net3 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
torch.nn.Linear(10, 1)
)
# 将保存的参数复制到 net3
net3.load_state_dict(torch.load('net_params.pkl'))
prediction = net3(x)
axes[1].cla()
axes[1].scatter(x.data.numpy(), y.data.numpy())
axes[1].plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
# 保存 net1 (1. 整个网络, 2. 只有参数)
save()
# 提取整个网络
restore_net()
# 提取网络参数, 复制到新网络
restore_params()
In [ ]:
In [ ]:
In [ ]: